diff options
| -rw-r--r-- | youtube_dl/extractor/__init__.py | 1 | ||||
| -rw-r--r-- | youtube_dl/extractor/criterion.py | 31 |
2 files changed, 32 insertions, 0 deletions
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index c00d5a352..494b1b9d3 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -8,6 +8,7 @@ from .breakcom import BreakIE from .brightcove import BrightcoveIE from .collegehumor import CollegeHumorIE from .comedycentral import ComedyCentralIE +from .criterion import CriterionIE from .cspan import CSpanIE from .dailymotion import DailymotionIE from .depositfiles import DepositFilesIE diff --git a/youtube_dl/extractor/criterion.py b/youtube_dl/extractor/criterion.py new file mode 100644 index 000000000..d1fe7fc3c --- /dev/null +++ b/youtube_dl/extractor/criterion.py @@ -0,0 +1,31 @@ +# -*- coding: utf-8 -*- + +import re + +from .common import InfoExtractor + +class CriterionIE(InfoExtractor): + _VALID_URL = r'http://www.criterion.com/films/(.*)' + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group(1).split('-')[0] + webpage = self._download_webpage(url, video_id) + + final_url = self._search_regex(r'so.addVariable\("videoURL", "(.+?)"\)\;', + webpage, 'video url') + title = self._search_regex(r'<meta content="(.+?)" property="og:title" />', + webpage, 'video title') + description = self._search_regex(r'<meta name="description" content="(.+?)" />', + webpage, 'video description') + thumbnail = self._search_regex(r'so.addVariable\("thumbnailURL", "(.+?)"\)\;', + webpage, 'thumbnail url') + ext = final_url.split('.')[-1] + + return {'id': video_id, + 'url' : final_url, + 'title': title, + 'ext': ext, + 'description': description, + 'thumbnail': thumbnail, + } |